AISB Convention 2015

The AISB Convention is an annual conference covering the range of AI and Cognitive Science, organised by the Society for the Study of Artificial Intelligence and Simulation of Behaviour. The 2015 Convention will be held at the Uni...


Yasemin Erden on BBC

AISB Committee member, and Philosophy Programme Director and Lecturer, Dr Yasemin J. Erden interviewed for the BBC on 29 October 2013. Speaking on the Today programme for BBC Radio 4, as well as the Business Report for BBC world N...


Mark Bishop on BBC ...

Mark Bishop, Chair of the Study of Artificial Intelligence and the Simulation of Behaviour, appeared on Newsnight to discuss the ethics of ‘killer robots’. He was approached to give his view on a report raising questions on the et...


AISB YouTube Channel

The AISB has launched a YouTube channel: ( The channel currently holds a number of videos from the AISB 2010 Convention. Videos include the AISB round t...


Lighthill Debates

The Lighthill debates from 1973 are now available on YouTube. You need to a flashplayer enabled browser to view this YouTube video  



AISB opportunities Bulletin Item

Postdoc Position - Adelaide, South Australia


Australian Centre for Visual Technologies
University of Adelaide
South Australia

Rapid interactive scene modelling from video

Research areas: Computer Vision, Structure from Motion

The successful applicant will join an established and successful team
lead by A/Prof Anton van den Hengel, Dr Anthony Dick, and Prof Philip 
Torr working on developing methods for rapid interactive scene modelling
from video sequences. The position is initially for 2 years and will be
available from mid 2008.

Project background: The recovery of 3D models from video has for a
number of years been a goal of both the computer vision and graphics
communities. In computer vision, several systems have been developed to
automatically recover a cloud of 3D scene points from a video sequence.
However these are vulnerable to ambiguities in the image data, 
degeneracies in camera motion, and a lack of discernible features on the
model surface. These difficulties can be overcome by manual intervention
in the modelling process. In the extreme case, a modelling package such
as Blender3D can used to build a model manually, but it is difficult to
create a photo-realistic result by this process. A more appealing option
is to use all of the information that can be derived from the video
using computer vision techniques to inform an interactive modelling
process. The question then arises: how should these interactions be
implemented so they are (a) intuitive to a non-expert user and (b)
powerful and informative to the underlying modelling engine, so that
only a small number of interactions are required? See for more details.

This is a new position in an expanding international group of 
researchers. Applicants should have a PhD in a relevant discipline, with 
a strong background in computer vision, in particular in structure from 
motion and Bayesian estimation.  Strong coding and mathematical skills 
are also required. The successful applicant will work as part of a team 
of researchers within the Australian Centre for Visual Technologies on
problems in interactive scene modelling.  International travel, 
particularly to work with researchers in Oxford, will be funded as part 
of the package.

Salary: From ,959 to ,982 (Australian Dollars) negotiable.

Closing Date: 30 April, 2008.  Further positions may become available, 
however, so applications may be accepted after this date for
those positions.

Informal enquiries and applications may be addressed to
A/Prof. A van den Hengel,
Computer Science
University of Adelaide,
South Australia 5005,
or by email to